Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations only say readOnlyHint=true; the description adds substantive behavior beyond that — owner scoping, that only manifest.json files in the deployment's artifact namespace are read and arbitrary S3 keys are not, that every row carries deploymentId so run IDs stay paired, and a timestamp/time-zone reporting caution. That is real operational context an agent could not derive from the schema or annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the scope sentence and the primary use case before the caveats, which is the right order. The time-zone paragraph, while a genuine trap to avoid, is three sentences long and dilutes an otherwise tight definition.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

No output schema exists, so the description should carry return-shape burden; it only discloses that rows include deploymentId, not what other fields a run record contains. The all-optional parameter set also leaves default behavior (no deploymentId given) undefined, which is a meaningful hole for a listing tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate. It does explain deploymentIds as "up to 10 related deployments" (matching maxItems: 10), but says nothing about `limit`, and — more importantly — all three parameters are optional, so it never states what happens when neither deploymentId nor deploymentIds is supplied.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ("Lists owner-scoped artifact runs") plus the two scoping modes (single deployment vs. up to 10 via deploymentIds). It implicitly separates itself from artifact-inspection siblings by emphasizing "runs" and "evidence available," but never names list_deployment_artifacts or get_deployment_artifact, so the distinction still requires the agent to infer it.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives an explicit trigger: "Use this when the user asks what evidence is available for a deployment, or before inspecting why an agent bought, sold, or did nothing" — a clear upstream-triage role. It lacks an explicit when-not or a pointer to the sibling that lists raw artifacts, so the boundary with list_deployment_artifacts is left unstated.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.